Document Image Analysis

@inproceedings{OGorman1996DocumentIA,
  title={Document Image Analysis},
  author={Lawrence O'Gorman and Rangachar Kasturi},
  year={1996}
}

Tables and Topics from this paper

Coordinating knowledge to improve optical music recognition
TLDR
Examining the implemented system’s behaviour clearly shows that this coordinated approach to OMR can correct many errors and can even identify some objects by only using syntactic information, based on the surrounding objects.
Turbo Recognition: An Approach to Decoding Page Layout
TLDR
The expressiveness of TR for describing abstract structure in two dimensions is explored, a hierarchy of grammars of increasing complexity is developed, and the application of the TR framework to the analysis of simple text documents is demonstrated.
Page layout analysis and classification for complex scanned documents
TLDR
The proposed page layout classifier can be used in systems for efficient document storage, content based document retrieval, optical character recognition, mobile phone imagery, and augmented reality.
Image Processing: Principles and Applications
This PDF file contains the editorial “Image Processing: Principles and Applications” for JEI Vol. 15 Issue 03
Document image analysis: A primer
TLDR
This paper briefly describes various components of a document analysis system and provides the background necessary to understand the detailed descriptions of specific techniques presented in other papers in this issue.
A tool for the in vivo gating of gene expression in neurons using the co-occurrence of neural activity and light
TLDR
This is the first optogenetic tool for the practical use of linking activity-dependent gene activation in response to direct nuclear calcium transduction and could be used in the future with behaviorally-driven neural activity.
General-Purpose OCR Paragraph Identification by Graph Convolution Networks
TLDR
A new approach for paragraph identification by spatial graph convolution networks (GCN) applied on OCR text boxes is proposed, which shows good generalization from synthetic training data to real-world images, and good adaptivity for variable document styles.
General-Purpose OCR Paragraph Identification by Graph Convolutional Neural Networks
TLDR
A new approach for paragraph identification by spatial graph convolutional neural networks (GCN) applied on OCR text boxes is proposed, which shows good generalization from synthetic training data to real-world images, and good adaptivity for variable document styles.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 35 REFERENCES
On the Detection of Dominant Points on Digital Curves
TLDR
A parallel algorithm for detecting dominant points on a digital closed curve is presented, which leads to the observation that the performance of dominant points detection depends not only on the accuracy of the measure of significance, but also on the precise determination of the region of support.
Curve fitting based on polygonal approximation,
  • Proc. 8th ICPR,
  • 1986
A fast sequential method for polygonal approximation of digitized curves
An Evaluation of Parallel Thinning Algorithms for Character Recognition
  • L. Lam, C. Suen
  • Computer Science
    IEEE Trans. Pattern Anal. Mach. Intell.
  • 1995
TLDR
The performance of 10 parallel thinning algorithms from this perspective is reported on by gathering statistics from their performance on large sets of data and examining the effects of the differentthinning algorithms on an OCR system.
Vector-Based Arc Segmentation in the Machine Drawing Understanding System Environment
  • D. Dori
  • Computer Science
    IEEE Trans. Pattern Anal. Mach. Intell.
  • 1995
TLDR
The high performance of the algorithm, demonstrated on a set of real engineering drawings, is due to the fact that it avoids both raster-to-vector and massive pixel-level operations, as well as any space transformations.
Detection of Dimension Sets in Engineering Drawings
TLDR
A new rule-based text/graphics separation algorithm and a model-based procedure for detecting arrowheads in any orientation have been developed for detecting dimension sets in engineering drawings drawn to ANSI drafting standards.
Interpretation of telephone system manhole drawings
TLDR
The authors have developed a skew correction algorithm for deskewing scanned images, a new rule-based text/graphics separation algorithm for separating annotations in the drawings, and a graphics interpretation system which includes model-based arrow head detection, splice detection, and recognition of interconnections of cables and stubs.
An interpretation system for land register maps
TLDR
It is shown that the image representation, vectorization techniques, and optical character recognition subsystem are quite general and that the methodology implemented in the system can be generalized to the acquisition of other classes of line drawings.
Analysis of Technical Documents: The REDRAW System
TLDR
The automated analysis of technical documents is a problem which has been worked on for several years in many kinds of applications, including flow charts, mechanical engineering, city maps, hand-drawn figures, and geographical maps.
Anatomy of a versatile page reader
TLDR
An experimental printed-page reader that is easy to adapt to various languages is described, and an attempt has been made to rid the algorithms of all language-specific rules, relying instead on automatic learning from examples and generalized table-driven methods.
...
1
2
3
4
...